5min chapter

Machine Learning Street Talk (MLST) cover image

ICLR 2020: Yoshua Bengio and the Nature of Consciousness

Machine Learning Street Talk (MLST)

CHAPTER

How to Learn a Sparse Factograph?

We have no idea of how to learn a sparse thing, we only know how to learn fully things. If what benjo says is true, we must be able to directly learn a sparse factograph because it's just too high dimensional. We can quantise and trim and prune after the fact, but we can learn sparse things like from the getgo. And if at some point you need to revise these connections, how are you going to do that without interating through each pair? Doesn't this get into the elephant in the room which is that it's not learnable yet? Wellii, humans are learning, so somehow it must be possible... But i don't think he

00:00

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode